A Survey on Dialog Management: Recent Advances and Challenges
arXiv:2005.02233
Abstract
Dialog management (DM) is a crucial component in a task-oriented dialog system. Given the dialog history, DM predicts the dialog state and decides the next action that the dialog agent should take. Recently, dialog policy learning has been widely formulated as a Reinforcement Learning (RL) problem, and more works focus on the applicability of DM. In this paper, we survey recent advances and challenges within three critical topics for DM: (1) improving model scalability to facilitate dialog system modeling in new scenarios, (2) dealing with the data scarcity problem for dialog policy learning, and (3) enhancing the training efficiency to achieve better task-completion performance . We believe that this survey can shed a light on future research in dialog management.
References in corpus (11)
- A Simple Language Model for Task-Oriented Dialogue
- Why We Need New Evaluation Metrics for NLG
- A User Simulator for Task-Completion Dialogues
- Multi-domain Dialogue State Tracking as Dynamic Knowledge Graph Enhanced Question Answering
- Structured Attention for Unsupervised Dialogue Structure Induction
- Agent-Agnostic Human-in-the-Loop Reinforcement Learning
- Budgeted Policy Learning for Task-Oriented Dialogue Systems
- Learning End-to-End Goal-Oriented Dialog with Maximal User Task Success and Minimal Human Agent Use
- Meta Dialogue Policy Learning
- Elastic CRFs for Open-ontology Slot Filling
- Transferable Dialogue Systems and User Simulators
Cited by in corpus (4)
- A Survey on Recent Advances and Challenges in Reinforcement Learning Methods for Task-Oriented Dialogue Policy Learning
- RiSAWOZ: A Large-Scale Multi-Domain Wizard-of-Oz Dataset with Rich Semantic Annotations for Task-Oriented Dialogue Modeling
- Augmenting Customer Support with an NLP-based Receptionist
- Slot Self-Attentive Dialogue State Tracking